File size: 2,241 Bytes
7a92993 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 | """
Test script for GptOssDense model with trust_remote_code=True
"""
from transformers import AutoConfig, AutoModelForCausalLM
import torch
# Test 1: Load config from Hub
print("=" * 60)
print("Test 1: Loading config from Hub")
print("=" * 60)
config = AutoConfig.from_pretrained(
'marksverdhei/gpt-oss-dense',
trust_remote_code=True
)
print(f"✓ Config loaded: {type(config).__name__}")
print(f" Model type: {config.model_type}")
print(f" Hidden size: {config.hidden_size}")
print(f" Num layers: {config.num_hidden_layers}")
print(f" Intermediate size: {config.intermediate_size}")
print(f" Num attention heads: {config.num_attention_heads}")
# Test 2: Initialize model from config
print("\n" + "=" * 60)
print("Test 2: Initializing model from config")
print("=" * 60)
model = AutoModelForCausalLM.from_config(
config,
trust_remote_code=True
)
print(f"✓ Model initialized: {type(model).__name__}")
# Test 3: Verify MLP structure
print("\n" + "=" * 60)
print("Test 3: Verifying MLP structure (Dense, not MoE)")
print("=" * 60)
mlp = model.model.layers[0].mlp
print(f"MLP type: {type(mlp).__name__}")
print(f" Has router: {hasattr(mlp, 'router')}")
print(f" Has experts: {hasattr(mlp, 'experts')}")
print(f" Has gate_up_proj: {hasattr(mlp, 'gate_up_proj')}")
print(f" Has down_proj: {hasattr(mlp, 'down_proj')}")
print(f" Alpha (GLU): {mlp.alpha}")
print(f" Limit (clamping): {mlp.limit}")
# Test 4: Forward pass
print("\n" + "=" * 60)
print("Test 4: Running forward pass")
print("=" * 60)
input_ids = torch.randint(0, config.vocab_size, (2, 16))
model.eval()
with torch.no_grad():
outputs = model(input_ids)
print(f"✓ Forward pass successful")
print(f" Input shape: {input_ids.shape}")
print(f" Output shape: {outputs.logits.shape}")
# Test 5: Parameter count
print("\n" + "=" * 60)
print("Test 5: Model parameters")
print("=" * 60)
total_params = sum(p.numel() for p in model.parameters())
print(f"Total parameters: {total_params:,}")
print("\n" + "=" * 60)
print("✅ All tests passed!")
print("=" * 60)
print("\nTo save the model weights:")
print(" model.save_pretrained('/path/to/save')")
print(" # Then upload to Hub with: huggingface-cli upload marksverdhei/gpt-oss-dense /path/to/save")
|